GeneSelectMMD (version 2.16.0)

errRates: Calculating FDR, FNDR, FPR, and FNR for a real microarray data set

Description

Calculating FDR, FNDR, FPR, and FNR for a real microarray data set based on the mixture of marginal distributions.

Usage

errRates(obj.gsMMD)

Arguments

obj.gsMMD

an object returned by gsMMD, gsMMD.default, gsMMD2, or gsMMD2.default

Value

A vector of 4 elements:

FDR

the percentage of nondifferentially expressed genes among selected genes.

FNDR

the percentage of differentially expressed genes among unselected genes.

FPR

the percentage of selected genes among nondifferentially expressed genes

FNR

the percentage of un-selected genes among differentially expressed genes

Details

We first fit the real microarray data set by the mixture of marginal distributions. Then we calculate the error rates based on the posterior distributions of a gene belonging to a gene cluster given its gene profiles. Please refer to Formula (7) on the page 6 of the paper listed in the Reference section.

References

Qiu, W.-L., He, W., Wang, X.-G. and Lazarus, R. (2008). A Marginal Mixture Model for Selecting Differentially Expressed Genes across Two Types of Tissue Samples. The International Journal of Biostatistics. 4(1):Article 20. http://www.bepress.com/ijb/vol4/iss1/20

Examples

  ## Not run: 
#     library(ALL)
#     data(ALL)
#     eSet1 <- ALL[1:100, ALL$BT == "B3" | ALL$BT == "T2"]
#     
#     mem.str <- as.character(eSet1$BT)
#     nSubjects <- length(mem.str)
#     memSubjects <- rep(0,nSubjects)
#     # B3 coded as 0, T2 coded as 1
#     memSubjects[mem.str == "T2"] <- 1
#     
#     obj.gsMMD <- gsMMD(eSet1, memSubjects, transformFlag = TRUE, 
#       transformMethod = "boxcox", scaleFlag = TRUE, quiet = FALSE)
#     round(errRates(obj.gsMMD), 3)
#   ## End(Not run)